Machine Learning-Aided Environmental Monitoring Solution to Identify Indoor Fungal Outbreaks

This study aims to propose a way to indirectly measure indoor fungi, which are known to be the causes of environmental diseases obtained in indoor life. For this purpose, MOFs-based multi-modal sensors for mVOCs will be developed, and machine learning algorithms to distinguish between general chemicals and mVOCs will be established. The detailed research plan is to develop MOFs-based multi-modal sensors capable of real-time measurement of mVOCs, and obtain fungal gas analysis data and indoor VOCs data. The collaborative study includes the sensor fabrication for VOCs measurement; and manufacturing technology for MOFs materials; and data integration by AI. The machine learning-aided environmental monitoring developed in this study will enable us to recognize indoor fungal outbreaks and provide a solution to protect our homes from fungal diseases.

Faculty Supervisor:

Seonghwan Kim

Student:

Partner:

Seoul National University of Science and Technology

Discipline:

Engineering

Sector:

Environmental Science and Technology; Nanotechnology; Artificial Intelligence

University:

University of Calgary

Program: